The predictive value of machine learning for mortality risk in patients with acute coronary syndromes: a systematic review and meta-analysis

Table 7 Accuracy for 3- or 6-month mortality

No	Model	Training cohort		Validation cohort
No	Model	Number of models	Accuracy (95%CI)	Number of models	ACC (95% CI)
1	LR	5	0.6977 [0.6622; 0.7310]	1	0.7218 [0.7069; 0.7363]
2	RF	2	0.7440 [0.6572; 0.8151]
3	ANN	3	0.7079 [0.6674; 0.7454]	1	0.7387 [0.7240; 0.7529]
4	DT	1	0.6969 [0.6824; 0.7110]
5	SVM	2	0.7233 [0.4934; 0.8752]
6	XGBoost	2	0.6937 [0.6446; 0.7387]
7	Overall	15	0.7089 [0.6737; 0.7418]	2	0.7303 [0.7184; 0.7418]

ISSN: 2047-783X